Method for processing channel state information, and terminal, base station and computer-readable storage medium

Abstract

Provided in the present disclosure is a method for processing channel state information, including: pre-processing original channel information to generate first channel information including a plurality of first channel information components; performing compression coding according to at least one first channel information component of the first channel information to generate second channel information; and feeding back channel state information including at least the second channel information. Further provided in the present disclosure are a terminal, a base station, and a computer-readable storage medium.

1 . A method for processing channel state information, comprising:
 pre-processing original channel information to generate first channel information comprising a plurality of first channel information components;   performing compression coding according to at least one first channel information component of the first channel information to generate second channel information; and   feeding back channel state information comprising at least the second channel information.   
     
     
         2 . The method according to  claim 1 , wherein pre-processing the original channel information to generate the first channel information comprises:
 generating a plurality of original channel information components according to the original channel information, wherein the original channel information components have the same dimension as the original channel information; and   stacking the plurality of the original channel information components to generate the first channel information, wherein one of the original channel information components constitutes one of the first channel information components.   
     
     
         3 . The method according to  claim 2 , wherein generating a plurality of original channel information components according to the original channel information comprises one of the following:
 extracting real parts of all elements in the original channel information to form a real part matrix as one of the original channel information components; and   extracting imaginary parts of all elements in the original channel information to form an imaginary part matrix as one of the original channel information components,   extracting absolute values of real parts of all elements in the original channel information to form a real part absolute value matrix as one of the original channel information components; extracting symbols of real parts of all elements in the original channel information to form a real part symbol matrix as one of the original channel information components; extracting absolute values of imaginary parts of all elements in the original channel information to form an imaginary part absolute value matrix as one of the original channel information components; and extracting symbols of imaginary parts of all elements in the original channel information to form an imaginary part symbol matrix as one of the original channel information components,   extracting amplitudes of all elements in the original channel information to form an amplitude matrix as one of the original channel information components; and extracting phases of all elements in the original channel information to form a phase matrix as one of the original channel information components.   
     
     
         4 - 5 . (canceled) 
     
     
         6 . The method according to  claim 2 , wherein performing compression coding according to at least one first channel information component of the first channel information to generate second channel information comprises:
 performing compression coding on each of the first channel information components to obtain the second channel information; and   feeding back channel state information comprises:   taking the second channel information as the channel state information for feedback.   
     
     
         7 . The method according to  claim 2 , wherein the plurality of first channel information components of the first channel information comprise a component to be compressed and a non-compressed component, performing compression coding according to at least one first channel information component of the first channel information to generate second channel information comprises:
 performing compression coding on a first channel information component serving as the component to be compressed to obtain the second channel information; and   feeding back channel state information comprises:   taking the second channel information and the first channel information component serving as the non-compressed component as the channel state information for feedback.   
     
     
         8 . The method according to  claim 1 , further comprising:
 before pre-processing the original channel information to generate first channel information, determining, according to channel characteristic information, a pre-processing mode for pre-processing the original channel information; and   feeding back information of the determined pre-processing mode to a base station.   
     
     
         9 . (canceled) 
     
     
         10 . The method according to  claim 1 , further comprising:
 before performing compression coding according to at least one first channel information component of the first channel information to generate second channel information, determining, according to channel characteristic information, a feedback mode for feeding back the channel state information, wherein the feedback mode indicates performing compression coding on all first channel information components of the first channel information, or performing compression coding on part of first channel information components of the first channel information; and   feeding back information of the determined feedback mode to a base station.   
     
     
         11 - 14 . (canceled) 
     
     
         15 . A method for processing channel state information, comprising:
 receiving channel state information comprising at least second channel information obtained by performing compression coding according to at least one first channel information component of first channel information, wherein the first channel information is obtained by pre-processing original channel information;   performing decompression decoding according to the second channel information to obtain third channel information; and   determining target channel information according to at least the third channel information.   
     
     
         16 . The method according to  claim 15 , wherein performing decompression decoding according to the second channel information to obtain third channel information comprises:
 decompressing the second channel information to obtain sixth channel information;   generating fourth channel information according to auxiliary channel information and the sixth channel information; and   decoding the fourth channel information to obtain the third channel information.   
     
     
         17 . The method according to  claim 16 , wherein generating fourth channel information according to auxiliary channel information and the sixth channel information comprises one of the following:
 stacking the auxiliary channel information and the sixth channel information to generate the fourth channel information,   generating a first vector according to the auxiliary channel information; generating a second vector according to the sixth channel information; and generating the fourth channel information from the first vector and the second vector.   
     
     
         18 . (canceled) 
     
     
         19 . The method according to  claim 17 , wherein generating the fourth channel information from the first vector and the second vector comprises:
 stacking the first vector and the second vector to generate a third vector; and   generating a channel matrix according to the third vector, and obtaining the fourth channel information.   
     
     
         20 . The method according to  claim 16 , further comprising:
 before performing decompression decoding according to the second channel information to obtain third channel information, pre-processing, according to pre-processing mode information for pre-processing the original channel information fed back by the terminal, uplink channel information according to a pre-processing mode for pre-processing the original channel information by the terminal, and   determining the auxiliary channel information according to the pre-processed uplink channel information.   
     
     
         21 . The method according to  claim 20 , wherein determining the auxiliary channel information according to the pre-processed uplink channel information comprises:
 forming, according to information of feedback mode fed back by the terminal, the auxiliary channel information from at least one uplink channel information component of the pre-processed uplink channel information, wherein information of the feedback mode indicates that the terminal performs compression coding on all first channel information components of the first channel information, or performs compression coding on part of first channel information components of the first channel information.   
     
     
         22 . The method according to  claim 15 , wherein the channel state information comprises the second channel information; and determining target channel information according to at least the third channel information comprises:
 performing, according to pre-processing mode information for pre-processing the original channel information fed back by the terminal, inverse processing on the third channel information to obtain the target channel information.   
     
     
         23 . The method according to  claim 15 , wherein the plurality of first channel information components of the first channel information comprise a non-compressed component and a component to be compressed; the second channel information is obtained by performing compression coding on the first channel information component serving as the component to be compressed; the channel state information comprises the second channel information and the first channel information component serving as the non-compressed component; and determining target channel information according to at least the third channel information comprises:
 integrating the third channel information with the first channel information component serving as the non-compressed component to obtain fifth channel information; and   performing, according to pre-processing mode information for pre-processing the original channel information fed back by the terminal, inverse processing on the fifth channel information to obtain the target channel information.   
     
     
         24 - 26 . (canceled) 
     
     
         27 . The method according to  claim 15 , further comprising:
 determining at least one of indexes of a plurality of pre-processing modes, indexes of a plurality of feedback modes, or indexes of neural network parameters of a plurality of sets of auto-encoders; and   configuring at least one of the indexes of the plurality of pre-processing modes, the indexes of the plurality of feedback modes, or the indexes of neural network parameters of the plurality of sets of auto-encoders to the terminal through at least one of physical layer signaling or higher-layer signaling.   
     
     
         28 . A terminal, comprising:
 at least one processor; and   a memory having at least one computer program stored thereon which, when executed by the at least one processor, causes the at least one processor to implement the method for processing channel state information according to any  claim 1 .   
     
     
         29 . A base station, comprising:
 at least one processor; and   a memory having at least one computer program stored thereon which, when executed by the at least one processor, causes the at least one processor to implement the method for processing channel state information according to  claim 15 .   
     
     
         30 . A non-transitory computer-readable storage medium having a computer program stored thereon which, when executed by a processor, causes the method for processing channel state information according to  claim 1  to be implemented. 
     
     
         31 . A non-transitory computer-readable storage medium having a computer program stored thereon which, when executed by a processor, causes the method for processing channel state information according to  claim 15  to be implemented.